-
document
-
Nurunnabi, A. (author), Teferle, F. N. (author), Laefer, D. F. (author), Lindenbergh, R.C. (author), Hunegnaw, A. (author)
Most deep learning (DL) methods that are not end-to-end use several multi-scale and multi-type hand-crafted features that make the network challenging, more computationally intensive and vulnerable to overfitting. Furthermore, reliance on empirically-based feature dimensionality reduction may lead to misclassification. In contrast, efficient...
journal article 2022
Source URL (retrieved on 2024-06-01 08:20): https://repository.tudelft.nl/islandora/search/collection%253Air?amp%3Bamp%3Bdisplay=tud_grid&%3Bamp%3Bf%5B0%5D=mods_genre_s%3A%22book%22&%3Bamp%3Bf%5B1%5D=mods_name_personal_author_namePart_family_ss%3A%22Meijer%22&%3Bamp%3Bf%5B2%5D=mods_name_personal_author_namePart_family_ss%3A%22Sheridan%22&%3Bamp%3Bsort=mods_originInfo_dateSort_dt%20asc&%3Bsort=mods_genre_s%20asc&collection=research&f%5B0%5D=mods_subject_topic_ss%3A%22Machine%5C%20Learning%22&f%5B1%5D=mods_name_personal_author_namePart_family_ss%3A%22Hunegnaw%22